{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:65LENYMP5AEO5CT7VDCCD3AU2O","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6545c839f80bc4e63467ee1a63f48c05a841200e2089c52f8d1a5cdd0c0def5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2026-05-14T08:28:57Z","title_canon_sha256":"98424ed4b2b79f191374b94e616f2c70afaa5f93838f0ec7f6066ce090e18c3a"},"schema_version":"1.0","source":{"id":"2605.14549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14549","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14549v1","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14549","created_at":"2026-05-17T23:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"65LENYMP5AEO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"65LENYMP5AEO5CT7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"65LENYMP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:3d5ddb020a583e61839366da8ffbe4b48ac0ee5c7dc69533e132b3987a557e2f","target":"graph","created_at":"2026-05-17T23:39:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CSG-Rerank gives a modest early-rank MRR gain over lexical BM25 under the strict policy, but does not reliably outperform BM25+symbol and does not improve Recall@10."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The source-visible proxy labels from proof references accurately stand in for the premises that would actually be needed in a realistic proof-generation or proof-repair setting."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CSLibPremiseBench shows that a structure-guided reranker provides only modest MRR gains over BM25 for premise retrieval in Lean 4 CS theorems and does not improve Recall@10."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval."}],"snapshot_sha256":"5af6aa15496abeae1536dd27d6e1b7a699fbbb412810a8fbd768c42e3c39994c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"CSLib is an emerging Lean 4 library for computer-science formalization, but its premise-retrieval behavior is not well represented by broad mathematical theorem-proving benchmarks. We introduce CSLibPremiseBench, a reproducible CSLib-specific benchmark and empirical study for source-visible premise retrieval over Lean 4 theorem and lemma declarations. The benchmark pins CSLib v4.29.0 at commit 0d37cc7fcc985cfc53b155e7eef2453f846c6da2, builds with Lean 4.29.0, and evaluates a strict import/source-order task set with 801 proxy-labelable tasks and 1875 CSLib candidate declarations. The labels are","authors_text":"Junye Ji","cross_cats":[],"headline":"CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2026-05-14T08:28:57Z","title":"CSLibPremiseBench: Structure-Guided Premise Retrieval and Label Robustness for Lean 4 Computer-Science Theorems"},"references":{"count":16,"internal_anchors":0,"resolved_work":16,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Leanexplore: A search engine for lean 4 declarations, 2025","work_id":"caf84e7b-650a-41e6-9de3-fe9a418e9ba8","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Ayers, Dragomir Radev, and Jeremy Avigad","work_id":"fa9350a1-82e0-40b6-84c8-9b63af97ad6b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Cslib: The lean computer science library, 2026","work_id":"183e90e1-b20e-409a-9cab-8a2fe5aebed8","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"The lean 4 theorem prover and programming language, 2021","work_id":"44987b9c-b745-4852-aee6-d3d9e9f8ccf0","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Computer science as infrastructure: the spine of the lean computer science library (cslib), 2026","work_id":"e7f1f2b8-0e8d-4475-8ada-1ab1b1d021a1","year":2026}],"snapshot_sha256":"cce310dbdecb00c476262cbad61cd6fd9f61c4398322b1bf2ed559efb5058bcd"},"source":{"id":"2605.14549","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:27:08.827243Z","id":"a064f180-b8bc-4063-b740-90574b937d56","model_set":{"reader":"grok-4.3"},"one_line_summary":"CSLibPremiseBench shows that a structure-guided reranker provides only modest MRR gains over BM25 for premise retrieval in Lean 4 CS theorems and does not improve Recall@10.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CSLibPremiseBench shows structure-guided reranking gives only modest early-rank gains over lexical baselines in Lean 4 computer-science premise retrieval.","strongest_claim":"CSG-Rerank gives a modest early-rank MRR gain over lexical BM25 under the strict policy, but does not reliably outperform BM25+symbol and does not improve Recall@10.","weakest_assumption":"The source-visible proxy labels from proof references accurately stand in for the premises that would actually be needed in a realistic proof-generation or proof-repair setting."}},"verdict_id":"a064f180-b8bc-4063-b740-90574b937d56"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9d6893c44f893015c07805cd27708c355341e4dcfb800a7b2287a3fb6a8d1cfa","target":"record","created_at":"2026-05-17T23:39:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6545c839f80bc4e63467ee1a63f48c05a841200e2089c52f8d1a5cdd0c0def5a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2026-05-14T08:28:57Z","title_canon_sha256":"98424ed4b2b79f191374b94e616f2c70afaa5f93838f0ec7f6066ce090e18c3a"},"schema_version":"1.0","source":{"id":"2605.14549","kind":"arxiv","version":1}},"canonical_sha256":"f75646e18fe808ee8a7fa8c421ec14d3af94e0efcd382441d3c33adb27d059fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f75646e18fe808ee8a7fa8c421ec14d3af94e0efcd382441d3c33adb27d059fd","first_computed_at":"2026-05-17T23:39:05.729714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:05.729714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rtFMe4ZUCdCYIpqQTLei/IZvEgRGNnIL6Y5Q5bNLA/8MjOs8wmFhyG0l+a+dQADLRM9O4Otc9vI23msucK21CQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:05.730239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d6893c44f893015c07805cd27708c355341e4dcfb800a7b2287a3fb6a8d1cfa","sha256:3d5ddb020a583e61839366da8ffbe4b48ac0ee5c7dc69533e132b3987a557e2f"],"state_sha256":"8704899643049fb0b9044421e4023c511f5d12147593042e0acc7f860d52a12e"}